Multiple-cluster adaptive training schemes

Abstract

This paper examines the training of multiple-cluster systems using adaptive training schemes. Various forms of transformation and canonical model are described in a consistent framework allowing re-estimation formulae for all cases to be simply derived. Initial experiments using these various schemes on a large vocabulary speech recognition task are presented. The initial experiments indicate that to achieve best performance when adapting these multiple-cluster systems requires the use of adaptive training schemes rather than using simpler cluster initialisation schemes.

DOI: 10.1109/ICASSP.2001.940842

Extracted Key Phrases

4 Figures and Tables

Cite this paper

@inproceedings{Gales2001MultipleclusterAT, title={Multiple-cluster adaptive training schemes}, author={Mark J. F. Gales}, booktitle={ICASSP}, year={2001} }